© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 105981
    Prev
    Next
    INDEX
    Explanations

    phrases related to time periods or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addin
    -0.07
     subsequent
    -0.07
     Duffy
    -0.07
    IPA
    -0.06
    oid
    -0.06
    lesh
    -0.06
    onium
    -0.06
    arine
    -0.06
    hq
    -0.06
     afterwards
    -0.05
    POSITIVE LOGITS
     ago
    0.10
     назад
    0.07
     jadx
    0.07
     önceki
    0.07
     ie
    0.07
    ÙĪÙĩ
    0.07
    ago
    0.07
    çi
    0.07
     earlier
    0.07
    andles
    0.07
    Activations Density 0.003%

    No Known Activations